INDEX

Explanations

references to round-trip related terms

oai_token-act-pair · gpt-3.5-turbo

phrases related to rounds and trips in specific contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Pepe

-0.72

parser

-0.67

ibly

-0.65

immers

-0.65

Peb

-0.63

 altered

-0.61

ratom

-0.61

 Lerner

-0.61

ingham

-0.60

Aly

-0.60

POSITIVE LOGITS

 applause

0.77

Winner

0.77

illon

0.73

Congratulations

0.72

 scrimmage

0.72

 congr

0.66

Ĥ¬

0.66

 Feature

0.64

asty

0.64

Õ

0.63

Activations Density 0.084%

references to round-trip related terms

phrases related to rounds and trips in specific contexts

No Comments

No Known Activations